Presentation 2021-12-13
Comment Extraction for Components for AR-based Product Review Browsing System
Shogo Anda, Masato Kikuchi, Tadachika Ozono,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this study, we are developing a system to support review browsing for each component of a product using augmented reality technology. In order to realize this system, it is necessary to collect comments about each component of the product. In this paper, we describe a method that uses BERT (Bidirectional Encoder Representations from Transformers) to extract evaluation attributes such as appearance or durability of a product's component from product reviews. In the evaluation experiments, we show that an average 88% recall rate and 85% Precision rate in our method by data augmentation considering the biased data in the reviews by generating similar reviews.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Augumented Reality / Review Classification / BERT
Paper # AI2021-8
Date of Issue 2021-12-06 (AI)

Conference Information
Committee AI
Conference Date 2021/12/13(1days)
Place (in Japanese) (See Japanese page)
Place (in English) Aimattain Hakata station
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Yuichi Sei(Univ. of Electro-Comm.)
Vice Chair Yuko Sakurai(AIST) / Tadachika Ozono(Nagoya Inst. of Tech.)
Secretary Yuko Sakurai(Tokyo Univ. of Agriculture and Technology) / Tadachika Ozono(Toho Univ.)
Assistant Kazutaka Matsuzaki(Chuo Univ.)

Paper Information
Registration To Technical Committee on Artificial Intelligence and Knowledge-Based Processing
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Comment Extraction for Components for AR-based Product Review Browsing System
Sub Title (in English)
Keyword(1) Augumented Reality
Keyword(2) Review Classification
Keyword(3) BERT
1st Author's Name Shogo Anda
1st Author's Affiliation Nagoya Institute of Technology(NIT)
2nd Author's Name Masato Kikuchi
2nd Author's Affiliation Nagoya Institute of Technology(NIT)
3rd Author's Name Tadachika Ozono
3rd Author's Affiliation Nagoya Institute of Technology(NIT)
Date 2021-12-13
Paper # AI2021-8
Volume (vol) vol.121
Number (no) AI-298
Page pp.pp.40-45(AI),
#Pages 6
Date of Issue 2021-12-06 (AI)